jazis-ai-marketplace

Intelligent git commit skill with Conventional Commits, automatic change decomposition into logical groups, and interactive approval workflow

Generate AGENTS.md, CONTRACTS.md, and INTEGRATIONS.md documentation for a module in a PHP modular monolith — domain, strategic and tactical design, published contracts, and consumed integrations

Multi-agent code review skill simulating JaziTheDev's review style — PR discipline, bugs and smells, project-rules compliance, historical context, code documentation, and tactical/strategic DDD. Posts findings as inline GitHub review comments.

Interview skill that relentlessly questions you about a plan or design — walking each branch of the decision tree one question at a time, with recommended answers — until you reach shared understanding. Adapted from Matt Pocock's skills collection.

Behavioral guidelines that reduce common LLM coding mistakes — surface assumptions, keep changes simple and surgical, and define verifiable success criteria. Derived from Andrej Karpathy's observations on LLM coding pitfalls, packaged from the multica-ai skills collection.

Turn a short brief into a well-structured Jira ticket — Context, Expected Result, GIVEN/WHEN/THEN acceptance criteria, and optional QA Notes and Implementation Plan expanders. Site- and project-agnostic; remembers your filing preferences and previews the full ticket before creating it.

Turn a short brief into a well-structured GitLab work item (Issue, Incident, Task, or Test case) — Context, Expected Result, GIVEN/WHEN/THEN acceptance criteria, and optional QA Notes and Implementation Plan as collapsible details. Creates via the glab CLI; repo-aware, remembers your fallback project, and previews the full work item before creating it.